Stock Price Predictions using Explainable AI

Predicting stock prices is not an easy job because the market keeps changing a lot and many outside things affect it. In this project, we are trying to build an Explainable AI (XAI) model that not only predicts stock prices but also explains how it came to those predictions. For this, we are using old stock data, market patterns, and some outside economic factors to train a special deep learning model that mixes LSTM (Long Short-Term Memory) and TFT (Temporal Fusion Transformer). Along with that, we are also using LIME (Local Interpretable Model-agnostic Explanations) to make the model’s thinking more clear by showing which factors are affecting the predictions. The results show that our model is giving accurate predictions and is also transparent in how it works. This explainable part helps investors and financial people understand how things like market trends, trading activity, and world events affect stock prices. We plan to make this model work inside a website or a desktop app, where users can see both the predictions and the reasons in a simple way. By adding explainability, we are making the system more trustworthy and useful for investors who want clear, data-based guidance.